I'm passionate about Video Understanding and Multi-modal Large Language Models (MLLMs).

• MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations.
  Kyungho Bae, Jinhyung Kim, Sihaeng Lee, Soonyoung Lee, Gunhee Lee, and Jinwoo Choi*.

• ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning.
  Jongseo Lee†, Kyungho Bae†, Kyle Min, Gyeongmoon Park, and Jinwoo Choi*.

• DEVIAS: Learning Disentangled Video Representations of Action and Scene for Holistic Video Understanding.
  Kyungho Bae†, Geo Ahn†, Youngrae Kim†, and Jinwoo Choi.
  ECCV 2024 Oral (acceptance rate = 2.33%).

• GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap.
  Hyogun Lee†, Kyungho Bae†, Yumin Ko, Seongjong Ha, Gyeongmoon Park, and Jinwoo Choi*.
  WACV 2024.

• Video Understanding
• Multi-modal Large Language Models (LLMs)